© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118483
    Prev
    Next
    INDEX
    Explanations

    SVG path commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    त्ते
    0.44
    Elis
    0.43
    ябрь
    0.41
    طيب
    0.40
    ጨ
    0.40
     Хер
    0.39
     αυτο
    0.39
    Sao
    0.37
    édéric
    0.36
    সেল
    0.36
    POSITIVE LOGITS
     Keyboard
    0.41
     Tried
    0.41
     Introductory
    0.40
     Precise
    0.38
     Tune
    0.38
    modeling
    0.37
     Reads
    0.37
     Tun
    0.37
    或其他
    0.37
    뛰
    0.37
    Activations Density 0.000%

    No Known Activations